​Graph-based deep learning literature
The repository contains links to

conference publications and the top 10 most cited publications
relevant workshops
surveys / literature reviews

https://github.com/naganandy/graph-based-deep-learning-literature

🔗 naganandy/graph-based-deep-learning-literature
links to conference publications in graph-based deep learning - naganandy/graph-based-deep-learning-literature

​Анализ кода ROOT — фреймворка для анализа данных научных исследований
Пока в Стокгольме проходила 118-я Нобелевская неделя, в офисе разработки статического анализатора кода PVS-Studio готовился обзор кода проекта ROOT, используемого в научных исследованиях для обработки больших данных. Премию за такой код, конечно, не дашь, а вот подробный обзор интересных дефектов кода и лицензию для полной проверки проекта разработчики получат.

Введение

ROOT — набор утилит для работы с данными научных исследований. Он обеспечивает все функциональные возможности, необходимые для обработки больших данных, статистического анализа, визуализации и хранения. В основном написан на языке C++. Разработка началась в CERN (Европейская организация по ядерным исследованиям) для исследований по физике высоких энергий. Каждый день тысячи физиков используют ROOT-приложения для анализа своих данных или для моделирования.

🔗 Анализ кода ROOT — фреймворка для анализа данных научных исследований
Пока в Стокгольме проходила 118-я Нобелевская неделя, в офисе разработки статического анализатора кода PVS-Studio готовился обзор кода проекта ROOT, используемог...

​Тренировочные наборы со скоростью звука (ну почти). Часть 1
Любой, не самый тривиальный (или просто редкий), объект с легкостью создаст массу проблем практически при каждой попытке применения нейронных сетей для решения реальных задач. Очевидно, отсутствие вменяемого тренировочного набора существенно усложняет подавляющее количество сценариев использования нейростевого подхода.

Как быть, например, с редким видом кузнечиков, распознавание представителей которого, по той или иной причине, стало очень важной задачей.

Все результаты (и примеры) получены самостоятельно и быстро.

🔗 Тренировочные наборы со скоростью звука (ну почти). Часть 1
Любой, не самый тривиальный (или просто редкий), объект с легкостью создаст массу проблем практически при каждой попытке применения нейронных сетей для решения р...

🎥 06. машинное обучение и ИИ
👁 1 раз ⏳ 3192 сек.
Ерёменко Максим Алексеевич,
Черток Андрей Викторович.
"Применение машинного обучения и искусственного интеллекта. Data Science сщщбщество в Сбербанке".
Расширенное заседание Совета по законодательному обеспечению развития цифровой экономики при Председателе Государственной Думы Федерального Собрания Российской Федерации.
25 сентября 2017 года.

​Michio Kaku: Future of Humans, Aliens, Space Travel & Physics | Artificial Intelligence (AI) Podcast

🔗 Michio Kaku: Future of Humans, Aliens, Space Travel & Physics | Artificial Intelligence (AI) Podcast
Michio Kaku is a theoretical physicist, futurist, and professor at the City College of New York. He is the author of many fascinating books on the nature of our reality and the future of our civilization. This conversation is part of the Artificial Intelligence podcast.

INFO:
Podcast website:
https://lexfridman.com/ai
iTunes:
https://apple.co/2lwqZIr
Spotify:
https://spoti.fi/2nEwCF8
RSS:
https://lexfridman.com/category/ai/feed/
Full episodes playlist:
https://www.youtube.com/playlist?list=PLrAXtmErZgOdP_8

​Audio and Visual Quality Measurement using Fréchet Distance

🔗 Audio and Visual Quality Measurement using Fréchet Distance
Posted by Kevin Kilgour, Software Engineer and Thomas Unterthiner, Research Software Engineer, Google Research, Zurich "I often say that...

​How Lyft Designs the Machine Learning Software Engineering Interview

🔗 How Lyft Designs the Machine Learning Software Engineering Interview
Iterations on revealing recurring patterns of thought, feeling, and behavior

🎥 Reinforcement Learning - The answer to automation. A deep dive: Oisin Boydell
👁 1 раз ⏳ 1530 сек.
www.predictconference.com

Predict is organised by Creme Global.
We provide data and models to decision makers.
www.cremeglobal.com
www.expertmodels.com

🎥 Ruslan Salakhutdinov (CMU) "Deep Learning: Recent Advances and New Challenges"
👁 1 раз ⏳ 3732 сек.
The lecture starts at 13:19.

Ruslan Salakhutdinov is a professor of computer science at the Carnegie Mellon University. Since 2009, he's published at least 42 papers on machine learning. His research has been funded by Google, Microsoft and Samsung. In 2016, Ruslan joined Apple as its director of AI research.

Abstract:
In the first part of the talk, Ruslan will introduce XLNet, a generalized autoregressive pretraining method that (1) enables learning bidirectional contexts by maximizing the expected likel

​Does the brain do backpropagation? CAN Public Lecture - Geoffrey Hinton - May 21, 2019

🔗 Does the brain do backpropagation? CAN Public Lecture - Geoffrey Hinton - May 21, 2019
Canadian Association for Neuroscience 2019 Public lecture: Geoffrey Hinton https://can-acn.org/2019-public-lecture-geoffrey-hinton

​The Fundamentals of Matplotlib

🔗 The Fundamentals of Matplotlib
Having a good grasp of these basics will greatly ease your foray into the expansive world of data visualization.

​A Gentle Introduction to Maximum Likelihood Estimation for Machine Learning

🔗 A Gentle Introduction to Maximum Likelihood Estimation for Machine Learning
Density estimation is the problem of estimating the probability distribution for a sample of observations from a problem domain. There are many techniques for solving density estimation, although a common framework used throughout the field of machine learning is maximum likelihood estimation. Maximum likelihood estimation involves defining a likelihood function for calculating the conditional probability …

​https://towardsdatascience.com/plotting-with-python-c2561b8c0f1f

🔗 Learn how to create beautiful and insightful charts with Python — the Quick, the Pretty, and the Awe
Data shows that money can buy happiness. A comprehensive code-along guide to visualization with Python, explaining plotting with Pandas…

​Quantum supremacy using a programmable superconducting processor

https://www.nature.com/articles/s41586-019-1666-5?fbclid=IwAR382bUHaSOgZpZDw7HMSAESLXQ_skyNW7Qza3UPivcUu_SmnW-XyUk9ez8

🔗 Quantum supremacy using a programmable superconducting processor
Quantum supremacy is demonstrated using a programmable superconducting processor known as Sycamore, taking approximately 200 seconds to sample one instance of a quantum circuit a million times, which would take a state-of-the-art supercomputer around ten thousand years to compute.

​DOAT: A Large-scale Dataset for Object DeTection in Aerial Images
Includes codes for detectors and transformers
https://captain-whu.github.io/DOTA/

🔗 DOTA

​User Churn Prediction using Neural Network with Keras

🔗 User Churn Prediction using Neural Network with Keras
Based on users’ first-week behavior in the app, we create a model to predict whether they churn in the first month.

🎥 Demonstrating Quantum Supremacy
👁 4 раз ⏳ 283 сек.
We’re marking a major milestone in quantum computing research that opens up new possibilities for this technology. Learn how the Google AI Quantum team demonstrated how a quantum computer can perform a task no classical computer can in an experiment called "quantum supremacy."

Subscribe to our Channel: https://www.youtube.com/google
Tweet with us on Twitter: https://twitter.com/google
Follow us on Instagram: https://www.instagram.com/google
Join us on Facebook: https://www.facebook.com/Google

​Kaggle Reading Group: EfficientNet (Part 2) | Kaggle

🔗 Kaggle Reading Group: EfficientNet (Part 2) | Kaggle
This week we'll be starting EfficientNet (Tan & Le, 2019), which was published at ICML 2019. The paper proposes a new family of models that are both smaller and faster to train than traditional convolutional neural networks. Link to paper: http://proceedings.mlr.press/v97/tan19a/tan19a.pdf SUBSCRIBE: https://www.youtube.com/c/kaggle?sub_... About Kaggle: Kaggle is the world's largest community of data scientists. Join us to compete, collaborate, learn, and do your data science work. Kaggle's platform is

​Splitting your data to fit any machine learning model

🔗 Splitting your data to fit any machine learning model
Split data set into train and test and separate features from the target with just a few lines of code using scikit-learn.

​Colorizing Images with a Convolutional Neural Network

🔗 Colorizing Images with a Convolutional Neural Network
What a Deep Learning algorithm says about composition, style, and the relationship between Machine Learning and the arts

​An Intuitive Explanation of GraphSAGE

🔗 An Intuitive Explanation of GraphSAGE
Inductive learning is useful in dynamic datasets. Here we discuss an inductive learning algorithm on graphs.